Saved in:
Bibliographic Details
Main Authors: Hasan, Adib, Roozbehani, Mardavij, Dahleh, Munther
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.17455
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916263313276928
author Hasan, Adib
Roozbehani, Mardavij
Dahleh, Munther
author_facet Hasan, Adib
Roozbehani, Mardavij
Dahleh, Munther
contents This paper introduces WeatherFormer, a transformer encoder-based model designed to learn robust weather features from minimal observations. It addresses the challenge of modeling complex weather dynamics from small datasets, a bottleneck for many prediction tasks in agriculture, epidemiology, and climate science. WeatherFormer was pretrained on a large pretraining dataset comprised of 39 years of satellite measurements across the Americas. With a novel pretraining task and fine-tuning, WeatherFormer achieves state-of-the-art performance in county-level soybean yield prediction and influenza forecasting. Technical innovations include a unique spatiotemporal encoding that captures geographical, annual, and seasonal variations, adapting the transformer architecture to continuous weather data, and a pretraining strategy to learn representations that are robust to missing weather features. This paper for the first time demonstrates the effectiveness of pretraining large transformer encoder models for weather-dependent applications across multiple domains.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17455
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle WeatherFormer: A Pretrained Encoder Model for Learning Robust Weather Representations from Small Datasets
Hasan, Adib
Roozbehani, Mardavij
Dahleh, Munther
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Atmospheric and Oceanic Physics
This paper introduces WeatherFormer, a transformer encoder-based model designed to learn robust weather features from minimal observations. It addresses the challenge of modeling complex weather dynamics from small datasets, a bottleneck for many prediction tasks in agriculture, epidemiology, and climate science. WeatherFormer was pretrained on a large pretraining dataset comprised of 39 years of satellite measurements across the Americas. With a novel pretraining task and fine-tuning, WeatherFormer achieves state-of-the-art performance in county-level soybean yield prediction and influenza forecasting. Technical innovations include a unique spatiotemporal encoding that captures geographical, annual, and seasonal variations, adapting the transformer architecture to continuous weather data, and a pretraining strategy to learn representations that are robust to missing weather features. This paper for the first time demonstrates the effectiveness of pretraining large transformer encoder models for weather-dependent applications across multiple domains.
title WeatherFormer: A Pretrained Encoder Model for Learning Robust Weather Representations from Small Datasets
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2405.17455